Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    cyclic data structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    쫙
    0.46
    䢍
    0.45
    图中
    0.41
    舸
    0.41
     wcex
    0.41
    Κα
    0.40
    🔉
    0.40
     直
    0.40
    ുണ്ട്
    0.39
    punyai
    0.39
    POSITIVE LOGITS
    を実施
    0.39
     Gallows
    0.39
    elman
    0.37
     inadequate
    0.37
     ($\
    0.37
     dio
    0.36
     выполнение
    0.36
    はお
    0.35
    一般的な
    0.35
     Sleeve
    0.35
    Act Density 0.000%

    No Known Activations